product-manager
Warn
Audited by Snyk on Apr 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md and references/integrations.md explicitly instruct the agent to connect to external MCP servers (e.g., registry.modelcontextprotocol.io, Jira/Confluence, GitHub, GitLab, Linear, Azure DevOps) and "pull real data" such as issues, Confluence product specs, and customer feedback—untrusted, user-generated third‑party content that the agent is expected to read and use to drive recommendations.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata